The rise of unmanned ``dark factories'' operating without human presence demands autonomous safety systems capable of detecting and responding to multiple hazard types. We present SafeGuard ASF (Agentic Security Fleet), a comprehensive framework deploying humanoid robots for autonomous hazard detection in industrial environments. Our system integrates multi-modal perception (RGB-D imaging), a ReAct-based agentic reasoning framework, and learned locomotion policies on the Unitree G1 humanoid platform. We address three critical hazard scenarios: fire and smoke detection, abnormal temperature monitoring in pipelines, and intruder detection in restricted zones. Our perception pipeline achieves 94.2% mAP for fire or smoke detection with 127ms latency. We train multiple locomotion policies, including dance motion tracking and velocity control, using Unitree RL Lab with PPO, demonstrating stable convergence within 80,000 training iterations. We validate our system in both simulation and real-world environments, demonstrating autonomous patrol, human detection with visual perception, and obstacle avoidance capabilities. The proposed ToolOrchestra action framework enables structured decision-making through perception, reasoning, and actuation tools.

翻译：无人值守的“暗工厂”的兴起，要求自主安全系统能够检测并应对多种危险类型。我们提出了SafeGuard ASF（Agentic Security Fleet），这是一个部署人形机器人在工业环境中进行自主危险检测的综合框架。该系统集成了多模态感知（RGB-D成像）、基于ReAct的代理推理框架，以及在Unitree G1人形平台上学习的运动控制策略。我们针对三种关键危险场景：火灾与烟雾检测、管道异常温度监测，以及受限区域入侵者检测。我们的感知流程在火灾或烟雾检测中实现了94.2%的mAP，延迟为127毫秒。我们使用配备PPO算法的Unitree RL Lab训练了多种运动控制策略，包括舞蹈动作追踪和速度控制，在8万次训练迭代内实现了稳定收敛。我们在仿真和真实环境中对系统进行了验证，展示了自主巡逻、基于视觉感知的人员检测以及避障能力。所提出的ToolOrchestra动作框架通过感知、推理和执行工具实现了结构化决策。